Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to infidelity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "inf," indicating words related to information or conditions that begin with "inf."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.84
    hyde
    -0.81
    BOOK
    -0.80
    soDeliveryDate
    -0.78
    DragonMagazine
    -0.74
    Downloadha
    -0.74
     Blitz
    -0.74
    manship
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    \\\\\\\\
    -0.72
    POSITIVE LOGITS
    usions
    1.13
    requent
    1.10
    requently
    1.08
    raction
    1.07
    acet
    1.05
    erno
    1.05
    ractions
    1.04
    idelity
    1.01
    acqu
    1.01
    luence
    0.99
    Act Density 0.009%

    No Known Activations